Training in progress, epoch 0, checkpoint

checkpoint-2289600/config.json

@@ -0,0 +1,28 @@
+{
+  "_remove_final_layer_norm": false,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 768,
+  "hidden_size": 768,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 512,
+  "model_type": "opt",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "pad_token_id": 1,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.3",
+  "use_cache": true,
+  "vocab_size": 50002,
+  "word_embed_proj_dim": 768
+}

checkpoint-2289600/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.33.3"
+}

checkpoint-2289600/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10708a87a4368e51064304b598553a0aaa65d9c10315f0eab728c2afcb6d2280
+size 537476677

checkpoint-2289600/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82a84c2d2b40aba3fd723a96be368f56c006d8b41d4c41ebcb6a5abdbab01abb
+size 268727709

checkpoint-2289600/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2e074b93a7e23c414db0ce3c79899923fe786b671de7695515d1213c5fcbf2c
+size 14511

checkpoint-2289600/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:561bbaf3ee599524235f24fbb9c6b1974bc1409524bb70783645695fd65ebbe3
+size 627

checkpoint-2289600/special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "<eos>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

checkpoint-2289600/tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<eos>",
+  "max_length": null,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}

checkpoint-2289600/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27ea7478e32255ec4b652a86c692980dba020d887cc938df5a1e4a571d37a460
+size 4283